Audio

The Audio API provides text-to-speech and audio transcription capabilities.

• Text-to-speech: convert text into audio
• Transcription: convert audio into text

Text-to-speech

Convert input text into an audio file.

Endpoint

POST https://api.nexusmodels.cn/v1/audio/speech

Headers

Authorization: Bearer YOUR_NEXUSMODELS_API_KEY
Content-Type: application/json

Request parameters

Parameter	Type	Required	Description
model	string	Yes	Text-to-speech model name
input	string	Yes	Text to convert into speech
voice	string	Yes	Voice name supported by the model
response_format	string	No	Output format, such as mp3 or wav
speed	number	No	Playback speed supported by the model

Example

curl -sS -X POST \
  'https://api.nexusmodels.cn/v1/audio/speech' \
  -H 'Authorization: Bearer YOUR_NEXUSMODELS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "YOUR_TTS_MODEL",
    "input": "Welcome to the NexusModels API.",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output nexusmodels-speech.mp3

Verify the output file

ls -lh nexusmodels-speech.mp3
file nexusmodels-speech.mp3

---

Transcription

Convert an audio file into text.

Endpoint

POST https://api.nexusmodels.cn/v1/audio/transcriptions

Headers

Authorization: Bearer YOUR_NEXUSMODELS_API_KEY
Content-Type: multipart/form-data

When using curl -F, do not manually set Content-Type. Curl automatically generates the correct boundary.

Request parameters

Parameter	Type	Required	Description
model	string	Yes	Audio transcription model name
file	file	Yes	Audio file to transcribe
language	string	No	Audio language, such as zh or en
prompt	string	No	Optional context to improve recognition
response_format	string	No	Response format, such as json or text
temperature	number	No	Controls transcription randomness

Example

curl -sS -X POST \
  'https://api.nexusmodels.cn/v1/audio/transcriptions' \
  -H 'Authorization: Bearer YOUR_NEXUSMODELS_API_KEY' \
  -F 'model=YOUR_TRANSCRIPTION_MODEL' \
  -F 'file=@audio.mp3' \
  -F 'language=en' \
  -F 'response_format=json'

Response example

{
  "text": "Welcome to the NexusModels API."
}